Skip to content

server : re-enable SWA speculative decoding #14131

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jun 12, 2025

Conversation

ggerganov
Copy link
Member

fix #13963

rel #14119 #14130

@ggerganov ggerganov changed the title server : re-enable swa speculative decoding server : re-enable SWA speculative decoding Jun 11, 2025
Base automatically changed from gg/batch-rework-multi-seq-inp to master June 12, 2025 07:02
@ggerganov ggerganov marked this pull request as ready for review June 12, 2025 07:32
@ggerganov ggerganov requested a review from ngxson as a code owner June 12, 2025 07:32
@ggerganov ggerganov force-pushed the gg/server-reenable-swa-spec branch from 51f245e to 36fce98 Compare June 12, 2025 08:51
@ggerganov ggerganov merged commit 7d51644 into master Jun 12, 2025
47 checks passed
s-Nick pushed a commit to s-Nick/llama.cpp that referenced this pull request Jun 16, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

Misc. bug: Using draft model with Gemma producing error "get_logits_ith: invalid logits id 0"
1 participant